From 20ef1262df418b2aa3abf988229f92893334481a Mon Sep 17 00:00:00 2001
From: Joey Hess <joeyh@joeyh.name>
Date: Thu, 27 Jun 2024 15:21:03 -0400
Subject: [PATCH] give proxied cluster nodes a higher cost than the cluster
 gateway

This makes eg git-annex get default to using the cluster rather than an
arbitrary node, which is better UI.

The actual cost of accessing a proxied node vs using the cluster is
basically the same. But using the cluster allows smarter load-balancing
to be done on the cluster.
---
 Remote/Git.hs                   | 14 ++++++++++++--
 doc/todo/git-annex_proxies.mdwn | 22 ++++++++++++++--------
 2 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/Remote/Git.hs b/Remote/Git.hs
index 89e0da38c1..844beb3b2e 100644
--- a/Remote/Git.hs
+++ b/Remote/Git.hs
@@ -176,6 +176,7 @@ configRead autoinit r = do
 			Just r' -> return r'
 		_ -> return r
 
+
 gen :: Git.Repo -> UUID -> RemoteConfig -> RemoteGitConfig -> RemoteStateHandle -> Annex (Maybe Remote)
 gen r u rc gc rs
 	-- Remote.GitLFS may be used with a repo that is also encrypted
@@ -186,10 +187,9 @@ gen r u rc gc rs
 		Nothing -> do
 			st <- mkState r u gc
 			c <- parsedRemoteConfig remote rc
-			go st c <$> remoteCost gc c defcst
+			go st c <$> remoteCost gc c (defaultRepoCost r)
 		Just addr -> Remote.P2P.chainGen addr r u rc gc rs
   where
-	defcst = if repoCheap r then cheapRemoteCost else expensiveRemoteCost
 	go st c cst = Just new
 	  where
 		new = Remote 
@@ -229,6 +229,11 @@ gen r u rc gc rs
 			, remoteStateHandle = rs
 			}
 
+defaultRepoCost :: Git.Repo -> Cost
+defaultRepoCost r
+	| repoCheap r = cheapRemoteCost
+	| otherwise = expensiveRemoteCost
+
 unavailable :: Git.Repo -> UUID -> RemoteConfig -> RemoteGitConfig -> RemoteStateHandle -> Annex (Maybe Remote)
 unavailable r = gen r'
   where
@@ -854,12 +859,17 @@ listProxied proxies rs = concat <$> mapM go rs
 		-- that cluster does not need to be synced with
 		-- by default, because syncing with the cluster will
 		-- effectively sync with all of its nodes.
+		--
+		-- Also, give it a slightly higher cost than the
+		-- cluster by default, to encourage using the cluster.
 		adjustclusternode clusters =
 			case M.lookup (ClusterNodeUUID (proxyRemoteUUID p)) (clusterNodeUUIDs clusters) of
 				Just cs
 					| any (\c -> S.member (fromClusterUUID c) proxieduuids) (S.toList cs) ->
 						addremoteannexfield SyncField
 							[Git.ConfigValue $ Git.Config.boolConfig' False]
+						. addremoteannexfield CostField 
+							[Git.ConfigValue $ encodeBS $ show $ defaultRepoCost r + 0.1]
 				_ -> id
 
 		proxieduuids = S.map proxyRemoteUUID proxied
diff --git a/doc/todo/git-annex_proxies.mdwn b/doc/todo/git-annex_proxies.mdwn
index a53197f8c1..29f662e6bf 100644
--- a/doc/todo/git-annex_proxies.mdwn
+++ b/doc/todo/git-annex_proxies.mdwn
@@ -41,14 +41,17 @@ For June's work on [[design/passthrough_proxy]], remaining todos:
   eg prefer to avoid using remotes that are doing other transfers at the
   same time.
 
-* The cost of a cluster and of its proxied nodes is currently all the same.
-  It would make sense for proxied nodes that are accessed via an intermedia
-  gateway to have a higher cost than proxied nodes that are accessed via
-  the remote gateway. And proxied nodes should generally have a higher cost
-  than the cluster, so that git-annex defaults to using the cluster.
-  (The cost of accessing a proxied node vs using the cluster is the same,
-  but using the cluster allows smarter load-balancing to be done on the
-  cluster. It also makes the UI not mention individual nodes.)
+* The cost of a proxied node that is accessed via an intermediate gateway
+  is currently the same as a node accessed via the cluster gateway.
+  To fix this, there needs to be some way to tell how many hops through
+  gateways it takes to get to a node. Currently the only way is to
+  guess based on number of dashes in the node name, which is not satisfying.
+
+  Even counting hops is not very satisfying, one cluster gateway could
+  be much more expensive to traverse than another one.
+
+  If seriously tackling this, it might be worth making enough information
+  available to use spanning tree protocol for routing inside clusters.
 
 * Optimise proxy speed. See design for ideas.
 
@@ -117,3 +120,6 @@ For June's work on [[design/passthrough_proxy]], remaining todos:
   protocol messages on to any remotes that have the same UUID as
   the cluster. Needs extension to P2P protocol to avoid cycles.
   (done)
+
+* Proxied cluster nodes should have slightly higher cost than the cluster
+  gateway. (done)
-- 
2.39.5